Region-wise Generative Adversarial ImageInpainting for Large Missing Areas
This addresses image restoration challenges for applications like photo editing, though it appears incremental as it builds on existing adversarial methods with specific architectural improvements.
The paper tackles the problem of image inpainting for large missing areas, where existing methods often produce artifacts and struggle with continuous regions, by proposing a region-wise adversarial framework with a correlation loss, resulting in significant outperformance over state-of-the-art approaches on three datasets.
Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless contents, such as color discrepancy, blur and artifacts. Moreover, most inpainting approaches cannot well handle the large continuous missing area cases. To address these problems, we propose a generic inpainting framework capable of handling with incomplete images on both continuous and discontinuous large missing areas, in an adversarial manner. From which, region-wise convolution is deployed in both generator and discriminator to separately handle with the different regions, namely existing regions and missing ones. Moreover, a correlation loss is introduced to capture the non-local correlations between different patches, and thus guides the generator to obtain more information during inference. With the help of our proposed framework, we can restore semantically reasonable and visually realistic images. Extensive experiments on three widely-used datasets for image inpainting tasks have been conducted, and both qualitative and quantitative experimental results demonstrate that the proposed model significantly outperforms the state-of-the-art approaches, both on the large continuous and discontinuous missing areas.